1 files changed, 95 insertions, 20 deletions

diff --git a/migration/rdma.c b/migration/rdma.c
index 5c2d113aa9..2a3c7889b9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -1117,19 +1117,82 @@ static int qemu_rdma_alloc_qp(RDMAContext *rdma)
     return 0;
 }
 
+/* Check whether On-Demand Paging is supported by RDAM device */
+static bool rdma_support_odp(struct ibv_context *dev)
+{
+    struct ibv_device_attr_ex attr = {0};
+    int ret = ibv_query_device_ex(dev, NULL, &attr);
+    if (ret) {
+        return false;
+    }
+
+    if (attr.odp_caps.general_caps & IBV_ODP_SUPPORT) {
+        return true;
+    }
+
+    return false;
+}
+
+/*
+ * ibv_advise_mr to avoid RNR NAK error as far as possible.
+ * The responder mr registering with ODP will sent RNR NAK back to
+ * the requester in the face of the page fault.
+ */
+static void qemu_rdma_advise_prefetch_mr(struct ibv_pd *pd, uint64_t addr,
+                                         uint32_t len,  uint32_t lkey,
+                                         const char *name, bool wr)
+{
+#ifdef HAVE_IBV_ADVISE_MR
+    int ret;
+    int advice = wr ? IBV_ADVISE_MR_ADVICE_PREFETCH_WRITE :
+                 IBV_ADVISE_MR_ADVICE_PREFETCH;
+    struct ibv_sge sg_list = {.lkey = lkey, .addr = addr, .length = len};
+
+    ret = ibv_advise_mr(pd, advice,
+                        IBV_ADVISE_MR_FLAG_FLUSH, &sg_list, 1);
+    /* ignore the error */
+    if (ret) {
+        trace_qemu_rdma_advise_mr(name, len, addr, strerror(errno));
+    } else {
+        trace_qemu_rdma_advise_mr(name, len, addr, "successed");
+    }
+#endif
+}
+
 static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
 {
     int i;
     RDMALocalBlocks *local = &rdma->local_ram_blocks;
 
     for (i = 0; i < local->nb_blocks; i++) {
+        int access = IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE;
+
         local->block[i].mr =
             ibv_reg_mr(rdma->pd,
                     local->block[i].local_host_addr,
-                    local->block[i].length,
-                    IBV_ACCESS_LOCAL_WRITE |
-                    IBV_ACCESS_REMOTE_WRITE
+                    local->block[i].length, access
                     );
+
+        if (!local->block[i].mr &&
+            errno == ENOTSUP && rdma_support_odp(rdma->verbs)) {
+                access |= IBV_ACCESS_ON_DEMAND;
+                /* register ODP mr */
+                local->block[i].mr =
+                    ibv_reg_mr(rdma->pd,
+                               local->block[i].local_host_addr,
+                               local->block[i].length, access);
+                trace_qemu_rdma_register_odp_mr(local->block[i].block_name);
+
+                if (local->block[i].mr) {
+                    qemu_rdma_advise_prefetch_mr(rdma->pd,
+                                    (uintptr_t)local->block[i].local_host_addr,
+                                    local->block[i].length,
+                                    local->block[i].mr->lkey,
+                                    local->block[i].block_name,
+                                    true);
+                }
+        }
+
         if (!local->block[i].mr) {
             perror("Failed to register local dest ram block!");
             break;
@@ -1215,28 +1278,40 @@ static int qemu_rdma_register_and_get_keys(RDMAContext *rdma,
      */
     if (!block->pmr[chunk]) {
         uint64_t len = chunk_end - chunk_start;
+        int access = rkey ? IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE :
+                     0;
 
         trace_qemu_rdma_register_and_get_keys(len, chunk_start);
 
-        block->pmr[chunk] = ibv_reg_mr(rdma->pd,
-                chunk_start, len,
-                (rkey ? (IBV_ACCESS_LOCAL_WRITE |
-                        IBV_ACCESS_REMOTE_WRITE) : 0));
-
-        if (!block->pmr[chunk]) {
-            perror("Failed to register chunk!");
-            fprintf(stderr, "Chunk details: block: %d chunk index %d"
-                            " start %" PRIuPTR " end %" PRIuPTR
-                            " host %" PRIuPTR
-                            " local %" PRIuPTR " registrations: %d\n",
-                            block->index, chunk, (uintptr_t)chunk_start,
-                            (uintptr_t)chunk_end, host_addr,
-                            (uintptr_t)block->local_host_addr,
-                            rdma->total_registrations);
-            return -1;
+        block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access);
+        if (!block->pmr[chunk] &&
+            errno == ENOTSUP && rdma_support_odp(rdma->verbs)) {
+            access |= IBV_ACCESS_ON_DEMAND;
+            /* register ODP mr */
+            block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access);
+            trace_qemu_rdma_register_odp_mr(block->block_name);
+
+            if (block->pmr[chunk]) {
+                qemu_rdma_advise_prefetch_mr(rdma->pd, (uintptr_t)chunk_start,
+                                            len, block->pmr[chunk]->lkey,
+                                            block->block_name, rkey);
+
+            }
         }
-        rdma->total_registrations++;
     }
+    if (!block->pmr[chunk]) {
+        perror("Failed to register chunk!");
+        fprintf(stderr, "Chunk details: block: %d chunk index %d"
+                        " start %" PRIuPTR " end %" PRIuPTR
+                        " host %" PRIuPTR
+                        " local %" PRIuPTR " registrations: %d\n",
+                        block->index, chunk, (uintptr_t)chunk_start,
+                        (uintptr_t)chunk_end, host_addr,
+                        (uintptr_t)block->local_host_addr,
+                        rdma->total_registrations);
+        return -1;
+    }
+    rdma->total_registrations++;
 
     if (lkey) {
         *lkey = block->pmr[chunk]->lkey;